{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T06:25:22Z","timestamp":1787034322329,"version":"build-2736575974"},"reference-count":43,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Digit. Health"],"abstract":"<jats:p>Wearable health monitoring systems provide continuous physiological measurements with growing use in clinical and population health applications. Baseline normalization enables individual-specific calibration of physiological signals to account for inter-subject variability; however, systematic evaluation of how the temporal relationship between normalization windows and evaluation data influences reported classification performance remains limited. Using physiological anxiety detection as a case study, we investigate this methodological challenge with the PhysioNet Spider Fear dataset (52 participants, including measurements of heart activity, skin conductance, and respiration), comparing normalization approaches and three baseline selection strategies. While maintaining strict subject-independent partitions, we show that including the normalized baseline in the evaluation window (test-inclusive baseline normalization) produced accuracies of 89%\u201393%, compared with when the baseline window is excluded (test-exclusive baseline normalization), which yielded 77%\u201385%, a 3\u201313 percentage-point difference consistent across classifiers, window sizes, and class-balance conditions. Two test-exclusive strategies using physiologically distinct baseline states (rest vs. anxiety) performed equivalently, indicating that performance differences were driven by temporal overlap rather than baseline selection. Full-feature normalization improved balanced accuracy by 11%\u201318% relative to unnormalized features; however, after removing temporal overlap, performance did not differ between normalization approaches. Prolonged stimulus exposure was associated with a 4\u20137 percentage-point reduction in balanced accuracy, consistent with habituation effects. Increasing window duration from 10\u2009s to 60\u2009s was associated with higher balanced accuracy (72%\u201374% vs. 78%\u201379%), whereas data augmentation did not improve performance under moderate class imbalance. We recommend explicit reporting of baseline temporal boundaries to enable accurate performance comparisons across studies and reliable assessment of clinical applicability in wearable health monitoring.<\/jats:p>","DOI":"10.3389\/fdgth.2026.1827279","type":"journal-article","created":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T05:37:25Z","timestamp":1787031445000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Baseline normalization choices inflate classification performance in wearable health monitoring: quantification and mitigation strategies"],"prefix":"10.3389","volume":"8","author":[{"given":"Alessandro","family":"Tognotti","sequence":"first","affiliation":[{"name":"Department of Electronics, Information and Bioengineering, Politecnico di Milano","place":["Milan, Italy"]},{"name":"Department of Health Sciences and Technology, ETH Zurich","place":["Zurich, Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Corin F.","family":"Otesteanu","sequence":"additional","affiliation":[{"name":"Department of Health Sciences and Technology, ETH Zurich","place":["Zurich, Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Anceschi","sequence":"additional","affiliation":[{"name":"Department of Health Sciences and Technology, ETH Zurich","place":["Zurich, Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlo","family":"Menon","sequence":"additional","affiliation":[{"name":"Department of Health Sciences and Technology, ETH Zurich","place":["Zurich, Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"e36","DOI":"10.1017\/S2045796021000275","article-title":"Global, regional, national burden of anxiety disorders from 1990 to 2019: results from the global burden of disease study 2019","volume":"30","author":"Yang","year":"2021","journal-title":"Epidemiol Psychiatr Sci"},{"key":"B2","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1186\/s43045-023-00315-3","article-title":"Epidemiology of anxiety disorders: global burden and sociodemographic associations","volume":"30","author":"Javaid","year":"2023","journal-title":"Middle East Curr Psychiatry"},{"key":"B3","doi-asserted-by":"publisher","first-page":"127","DOI":"10.31887\/DCNS.2017.19.2\/dstein","article-title":"Epidemiology of anxiety disorders: from surveys to nosology and back","volume":"19","author":"Stein","year":"2017","journal-title":"Dialogues Clin Neurosci"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1478851","DOI":"10.3389\/fcomp.2024.1478851","article-title":"Detection and monitoring of stress using wearables: a systematic review","author":"Pinge","year":"2024","journal-title":"Front. Comput. Sci"},{"key":"B5","doi-asserted-by":"publisher","first-page":"e13613","DOI":"10.1371\/journal.pone.0231517","article-title":"Online anxiety level detection from biosignals: machine learning based on a randomized controlled trial with spider-fearful individuals","volume":"57","author":"Ihmig","year":"2020","journal-title":"Psychophysiology"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1109\/BHI50953.2021.9508589","article-title":"Respiratory markers significantly enhance anxiety detection using multimodal physiological sensing","author":"Gazi","year":"2021","journal-title":"2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI)"},{"key":"B7","doi-asserted-by":"publisher","first-page":"3210","DOI":"10.3390\/s24103210","article-title":"Strategies for reliable stress recognition: a machine learning approach using heart rate variability features","volume":"24","author":"Bahameish","year":"2024","journal-title":"Sensors"},{"key":"B8","author":"Khullar","year":""},{"key":"B9","author":"Vulpe-Grigor\u0103si","year":""},{"key":"B10","doi-asserted-by":"publisher","first-page":"4098","DOI":"10.3390\/s21124098","article-title":"Analysis of default mode network in social anxiety disorder: EEG resting-state effective connectivity study","volume":"21","author":"Al-Ezzi","year":"2021","journal-title":"Sensors"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1794","DOI":"10.3390\/diagnostics12081794","article-title":"Machine learning for anxiety detection using biosignals: a review","volume":"12","author":"Ancillon","year":"2022","journal-title":"Diagnostics"},{"key":"B12","doi-asserted-by":"publisher","first-page":"2873","DOI":"10.3390\/s21082873","article-title":"HRV features as viable physiological markers for stress detection using wearable devices","volume":"21","author":"Dalmeida","year":"2021","journal-title":"Sensors"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1829","DOI":"10.1038\/s41467-024-46150-w","article-title":"Data leakage inflates prediction performance in connectome-based machine learning models","volume":"15","author":"Rosenblatt","year":"2024","journal-title":"Nat Commun"},{"key":"B14","doi-asserted-by":"publisher","first-page":"4154","DOI":"10.3390\/s25134154","article-title":"Optimizing mental stress detection via heart rate variability feature selection","volume":"25","author":"Behradfar","year":"2025","journal-title":"Sensors"},{"key":"B15","author":"Sasse","year":""},{"key":"B16","author":"Rajabi","year":""},{"key":"B17","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1186\/s13063-018-2554-2","article-title":"Effects of heart rate variability biofeedback during exposure to fear-provoking stimuli within spider-fearful individuals: study protocol for a randomized controlled trial","volume":"19","author":"Sch\u00e4fer","year":"2018","journal-title":"Trials"},{"key":"B18","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1038\/s41597-025-04908-x","article-title":"SpiderPhy dataset: a multimodal dataset of physiological, psychometric and behavioral responses to fear stimuli","volume":"12","author":"Lor","year":"2025","journal-title":"Sci Data"},{"key":"B19","doi-asserted-by":"publisher","first-page":"e1829","DOI":"10.7717\/peerj-cs.1829","article-title":"A comprehensive exploration of machine learning techniques for EEG-based anxiety detection","volume":"10","author":"Aldayel","year":"2024","journal-title":"PeerJ Comput Sci"},{"key":"B20","author":"Ihmig","year":""},{"key":"B21","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/TITS.2005.848368","article-title":"Detecting stress during real-world driving tasks using physiological sensors","volume":"6","author":"Healey","year":"2005","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1689","DOI":"10.3758\/s13428-020-01516-y","article-title":"NeuroKit2: a python toolbox for neurophysiological signal processing","volume":"53","author":"Makowski","year":"2021","journal-title":"Behav Res Methods"},{"key":"B23","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1109\/TBME.1985.325532","article-title":"A real-time QRS detection algorithm","author":"Pan","year":"1985","journal-title":"IEEE Trans Biomed Eng"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering9110711","article-title":"Heart and breathing rate variations as biomarkers for anxiety detection","volume":"9","author":"Ritsert","year":"2022","journal-title":"Bioengineering"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1226","DOI":"10.1109\/TPAMI.2005.159","article-title":"Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy","volume":"27","author":"Peng","year":"2005","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"B26","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach Learn"},{"key":"B27","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"B28","author":"Chen","year":""},{"key":"B29","author":"Hollmann","year":""},{"key":"B30","author":"Brodersen","year":""},{"key":"B31","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1145\/1007730.1007735","article-title":"A study of the behavior of several methods for balancing machine learning training data","volume":"6","author":"Batista","year":"2004","journal-title":"ACM SIGKDD Explor Newsl"},{"key":"B32","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","article-title":"Smote: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J Artif Intell Res"},{"key":"B33","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1080\/01621459.1937.10503522","article-title":"The use of ranks to avoid the assumption of normality implicit in the analysis of variance","volume":"32","author":"Friedman","year":"1937","journal-title":"J Am Stat Assoc"},{"key":"B34","doi-asserted-by":"publisher","first-page":"80","DOI":"10.2307\/3001968","article-title":"Individual comparisons by ranking methods","volume":"1","author":"Wilcoxon","year":"1945","journal-title":"Biom Bull"},{"key":"B35","first-page":"65","article-title":"A simple sequentially rejective multiple test procedure","volume":"6","author":"Holm","year":"1979","journal-title":"Scand J Stat"},{"key":"B36","author":"Nemenyi","year":""},{"key":"B37","first-page":"1","article-title":"Statistical comparisons of classifiers over multiple data sets","volume":"7","author":"Dem\u0161ar","year":"2006","journal-title":"J Mach Learn Res"},{"key":"B38","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1214\/aoms\/1177732186","article-title":"The problem of m rankings","volume":"10","author":"Kendall","year":"1939","journal-title":"Ann Math Stat"},{"key":"B39","doi-asserted-by":"publisher","first-page":"e0138921","DOI":"10.1371\/journal.pone.0138921","article-title":"Validity of (ultra-)short recordings for heart rate variability measurements","volume":"10","author":"Munoz","year":"2015","journal-title":"PLoS One"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-28090-7","article-title":"Measures of the psychophysiological response to recurrent anticipatory stress: the influence of neuroticism on heart rhythm and skin resistance","volume":"15","author":"Wagenblast","year":"2025","journal-title":"Sci Rep"},{"key":"B41","author":"Lamichhane","year":""},{"key":"B42","doi-asserted-by":"publisher","first-page":"7802","DOI":"10.3390\/s21237802","article-title":"Real-time stress level feedback from raw ECG signals for personalised, context-aware applications using lightweight convolutional neural network architectures","volume":"21","author":"Tzevelekakis","year":"2021","journal-title":"Sensors"},{"key":"B43","doi-asserted-by":"publisher","first-page":"1737585","DOI":"10.3389\/fphys.2025.1737585","article-title":"Advancing parkinson\u2019s disease detection through multi-dimensional machine learning: a comprehensive framework using wearable movement sensor analytics","volume":"16","author":"Xiang","year":"2026","journal-title":"Front Physiol"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1827279\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T05:37:31Z","timestamp":1787031451000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1827279\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,18]]},"references-count":43,"alternative-id":["10.3389\/fdgth.2026.1827279"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2026.1827279","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,18]]},"article-number":"1827279"}}